I am a Postdoctoral researcher at the University of Amsterdam, working with with Prof. Cees Snoek. I completed my PhD at the University of Bristol, advised by Prof. Dima Damen and Prof. Walterio Mayol-Cuevas. My area of interest is Video Understanding, with my PhD thesis (which you can find here) focussing on Skill Determination. I am particularly interested in fine-grained and long term video understanding with weak, noisy or other forms of incomplete supervision.

Contact: hazel.doughty *at* uva.nl

News & Activities


Publications


Day2Dark: Pseudo-Supervised Activity Recognition beyond Silent Daylight
Yunhua Zhang, Hazel Doughty, Cees Snoek
ArXiv, 2022.
[arXiv]
How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?
Fida Mohammad Thoker, Hazel Doughty, Piyush Bagad, Cees Snoek
European Conference on Computer Vision (ECCV), 2022.
[Webpage] [arXiv] [Code]
How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs
Hazel Doughty and Cees Snoek
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[Webpage] [arXiv] [Dataset and Code]
Audio-Adaptive Activity Recognition Across Video Domains
Yunhua Zhang, Hazel Doughty, Ling Shao, Cees Snoek
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[Webpage] [arXiv] [Code]
Skeleton-Contrastive 3D Action Representation Learning
Fida Mohammad Thoker, Hazel Doughty, Cees Snoek
ACM International Conference on Multimedia (ACMMM), 2021
[arXiv] [Code]
On Semantic Similarity in Video Retrieval
Michael Wray, Hazel Doughty and Dima Damen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[Webpage] [arXiv]
Rescaling Egocentric Vision: EPIC-KITCHENS-100
Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Antonino Furnari, Evangelos Kazakos, Jian Ma, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray
International Journal of Computer Vision (IJCV), 2021.
[Webpage] [arXiv] [Dataset and Code]
Action Modifiers: Learning from Adverbs in Instructional Videos
Hazel Doughty, Ivan Laptev, Walterio Mayol-Cuevas and Dima Damen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
[Webpage] [arXiv] [Dataset and Code]
The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020.
[arXiv Preprint]
The Pros and Cons: Rank-Aware Temporal Attention for Skill Determination in Long Videos
Hazel Doughty, Walterio Mayol-Cuevas and Dima Damen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[Webpage] [arXiv] [Dataset & Code]
Scaling Egocentric Vision: The EPIC-Kitchens Dataset
Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray
European Conference on Computer Vision (ECCV), 2018. (Oral)
[arXiv] [Webpage & Dataset]
Who's Better? Who's Best? Pairwise Deep Ranking for Skill Determination
Hazel Doughty, Dima Damen and Walterio Mayol-Cuevas
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (Spotlight)
[arXiv] [Bibtex] [Dataset]

People




Academic Service



Organizer: Netherlands Conference on Computer Vision, NeurIPS'21 Workshop on Pre-registration in ML, ICCV'21 Workshop on Structured Representations for Video Understanding, WiCV@CVPR2020, EPIC@CVPR2020, EPIC@ECCV2020
Reviewer: CVPR 2019-2022, ICCV 2019-2021, ECCV 2020-2022, TPAMI 2020-2022, IJCV 2021-2022, NeurIPS 2022, ACCV 2020, WACV 2020-2021, AAAI 2019
Outstading Reviewer: ICCV 2021, CVPR 2021, ECCV 2022 and 2020, ACCV 2020

Teaching



Unit Coordinator: Leren en Beslissen (Learning and Decision Making), 2022 (BSc AI, Y2)
Guest Lecture: Computer Vision 2, 2021